prompt-engineering
Interactive prompt optimization workflow for LLMs. Use when optimizing, improving, or engineering prompts for Claude, GPT, Gemini, or other language models; covers analysis, model-specific techniques, few-shot examples, XML structuring, and validation.
npx skills add majiayu000/claude-skill-registry --skill prompt-engineering-outlinedriven-odin-claude-plugin --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Interactive Prompt Optimization Workflow Execute this workflow to systematically improve any prompt for optimal LLM performance. ## Step 1: Analyze Current State Gather baseline information about your prompt optimization task: - **Current prompt**: Capture the exact prompt you want to optimize - **Target model**: Identify the specific model (Claude 4.5, Gemini 3.0, GPT 5.1, etc.) - **Use case**: Clarify the primary purpose (coding agent, analysis, content generation, conversation) - **Failure cases**: Document specific examples where current prompt fails or underperforms - **Success criteria**: Define measurable outcomes (accuracy, format compliance, response time) - **Test cases**: Create 3-5 representative examples for validation ## Step 2: Identify Model Type Determine the correct prompting approach based on model architecture: **Reasoning Models** (Claude 4.x, Gemini 3.0, GPT o-series, DeepSeek-R1): - **AVOID** explicit CoT phrases like "think step-by-step" or "let's work through this" - **PROVIDE** rich context with all relevant information upfront - **LET** the model's internal reasoning handle the thinking process **Non-Reasoning Models** (GPT-4o, GPT-4.1, Claude with thin
- Step 1: Analyze Current State
- Step 2: Identify Model Type
- Step 3: Select Core Techniques
- Step 4: Apply Techniques Systematically
- Step 5: Test and Validate
- Step 6: Deliver Optimized Prompt
What does the prompt-engineering skill do?
Interactive prompt optimization workflow for LLMs. Use when optimizing, improving, or engineering prompts for Claude, GPT, Gemini, or other language models; covers analysis, model-specific techniques, few-shot examples, XML structuring, and validation.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-engineering-outlinedriven-odin-claude-plugin --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.